Systems and methods for automatically determining object information and systems and methods for control based on automatically determined object information

• US 20070071328A1
• Filed: 09/28/2005
• Published: 03/29/2007
• Est. Priority Date: 09/28/2005
• Status: Active Grant

• Current Assignee: Wisconsin Alumni Research Foundation (University of Wisconsin System)
• Original Assignee: Wisconsin Alumni Research Foundation (University of Wisconsin System)
• Inventors: Ferrier, Nicola, Rawlings, James, Larsen, Paul
• Granted Patent: US 7,885,467 B2
• Time in Patent Office: Days
• US Class Current: 382/225
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30108 Industrial image inspection
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/12 Edge-based segmentation

Abstract

An image of high-aspect-ratio objects is analyzed to locate linear features within the image. The gradient direction for each pixel is determined, and connected pixels having similar gradient directions are grouped into line support regions. A linear feature is determined for each line support region. The linear features are analyzed to identify those that are co-linear. The linear features are then analyzed to find groups that are parallel and that sufficiently overlap. Additional sets of linear features that intersect the identified group are combined into that group. The line support regions of the grouped linear features are analyzed to determine representative orientation and/or dimensional information, which is analyzed to determine statistical information about a plurality of the objects. This information is used to monitor or control one or more processes associated with the objects, to reject the objects or a structure or device comprising the objects, or the like.

Claims

1. A method for locating objects in an image containing at least one object to be located, comprising:

obtaining an image comprising a plurality of pixels having image values;

segmenting the plurality of pixels of the obtained image to locate linear features occurring within the image;

analyzing the located linear features at least to identify pairs of located linear features that are co-linear;

clustering subsets of the located linear features based on the analysis of the located linear features to determine at least one linear feature for the clustered subset of located linear features, wherein at least one linear feature for the clustered subset of located linear features corresponds to one of the objects to be located in the image.

2. The method of claim 1, wherein segmenting the plurality of pixels of the obtained image to locate linear features occurring within the image comprises:

determining, for each pixel, a gradient direction for the image value of that pixel;

applying at least one gradient direction quantization map to the determined gradient directions for the plurality of pixels to generate at least one quantized gradient direction for each of the plurality of pixels;

determining, for each applied gradient quantization map, at least one connected component within the plurality of pixels, based on the quantized gradient directions for the plurality of pixels associated with that applied gradient quantization map; and

determining, for each of at least some of the determined connected components, at least one linear feature for that connected component.

3. The method of claim 2, further comprising, if a plurality of gradient quantization maps are applied to the determined gradient directions for the plurality of pixels, determining, for any connected components for different gradient quantization maps that contain at least one pixel in common, one of those connected components to be used when determining the at least one linear feature.

4. The method of claim 2, wherein analyzing the located linear features at least to identify pairs of located linear features that are co-linear comprises:

selecting a pair of elements from a set of elements comprising at least the determined linear features;

determining at least one co-linearity parameter for the selected pair of elements;

comparing, for at least one co-linearity requirement, at least one corresponding co-linearity parameter with that co-linearity requirement; and

if a determined number of the at least one co-linearity requirement are met, adding a virtual line determined based on at least the selected pair of elements to a set of elements comprising at least the virtual lines.

5. The method of claim 4, further comprising repeating the selecting, determining, comparing, and adding steps for at least one other pair of elements selected from the set of elements.

6. The method of claim 5, wherein repeating the selecting, determining comparing, and adding steps for at least one other pair of elements selected from the set of elements comprising repeating the selecting, determining, comparing, and adding steps for each other pair of elements selected from the set of elements.

7. The method of claim 4, wherein adding the determined virtual line to a set of elements comprising at least the virtual lines comprises adding the determined virtual line to the set of elements that comprises at least the determined linear features.

8. The method of claim 4, further comprising:

selecting a pair of elements from a set of elements comprising at least the determined linear features and the added virtual lines;

determining if the selected pair is a valid pair;

determining, if the selected pair is a valid pair, at least one parallelism parameter for the selected pair of elements;

comparing, for each of at least one parallelism requirement, at least one corresponding parallelism parameter with that parallelism requirement; and

if a determined number of the at least one parallelism requirement are met;

determining a significance value for the selected pair of elements, and

adding the selected pair of elements, along with the determined significance value, to a set of element pairs that met the determined number of the at least one parallelism requirement.

9. The method of claim 8, wherein clustering subsets of the located linear features comprises:

selecting, from the set of element pairs that met the determined number of the at least one parallelism requirement, a pair of elements in the set having a greatest significance value;

determining, if the selected pair of elements includes at least one virtual line, the linear features associated with that virtual line;

selecting, from the set of element pairs that met the determined number of the at least one parallelism requirement, any pairs of elements that include at least one of the pair of selected elements having the greatest significance value and any pairs of elements that include at least one of the determined linear features associated with at least one of the pair of selected elements having the greatest significance value;

determining, if any of the newly selected pair of elements includes at least one virtual line, the linear features associated with that virtual line;

creating a cluster of linear features from the linear features in the selected pairs of elements and the linear features determined to be associated with any selected virtual lines;

combining the connected components associated with the cluster of linear components; and

determining at least one linear feature corresponding to the combined connected components as the at least one linear feature for the clustered subset of located linear features.

10. The method of claim 1, further comprising determining at least one parameter for the clustered subsets of the linear features.

11. The method of claim 10, further comprising:

generating at least one control signal based on the at least one determined parameter;

outputting at least one of the at least one generated control signal to at least one controllable device; and

for each at least one controllable device to which at least one generated control signal is output, controlling at least one function of that controllable device based on the at least one control signal output to that controllable device.

12. The method of claim 11, wherein the at least one controllable device is at least one of a controllable actuator, a controllable signaling device and a programmed computing device programmed to perform at least one function in response to the at least one control signal.

13. The method of claim 10, further comprising:

generating at least one data signal based on the at least one determined parameter;

outputting the at least one generated data signal to at least one device; and

for each at least one device to which at least one generated data signal is output, performing at least one function of that device based on the at least one data signal output to that device.

14. The method of claim 13, wherein the at least one device is at least one of a controllable actuator, a signaling device, a control signal generating device that generates at least one control signal based on the at least one data signal and a programmed computing device programmed to perform at least one function in response to the at least one data signal.

15. The method of claim 10, further comprising

determining at least one statistical measure based on the at least one determined parameter;

generating at least one control signal based on the at least one determined statistical measure;

outputting at least one of the at least one generated control signal to at least one controllable device; and

for each at least one controllable device to which at least one generated control signal is output, controlling at least one function of that controllable device based on the at least one control signal output to that controllable device.

16. The method of claim 15, wherein the at least one controllable device is at least one of a controllable actuator, a controllable signaling device and a programmed computing device programmed to perform at least one function in response to the at least one control signal.

17. The method of claim 10, further comprising:

determining at least one statistical measure based on the at least one determined statistical measure;

generating at least one data signal based on the at least one statistical measure;

outputting the at least one generated data signal to at least one device; and

for each at least one device to which at least one generated data signal is output, performing at least one function of that device based on the at least one data signal output to that device.

18. The method of claim 17, wherein the at least one device is at least one of a controllable actuator, a signaling device, a control signal generating device that generates at least one control signal based on the at least one data signal and a programmed computing device programmed to perform at least one function in response to the at least one data signal.

19. The method of claim 10, further comprising

determining at least one statistical measure based on the at least one determined parameter;

outputting at least one of at least one control signal and at least one information signal based on at least one of at least one of the at least one determined parameter and at least one of the at least one determined statistical measure to at least one device; and

for each at least one device to which at least one generated control or information signal is output, controlling at least one function of that device based on the at least one control or information signal output to that device.

20. The method of claim 19, wherein the at least one device is at least one of a controllable actuator, a signaling device, a control signal generating device that generates at least one control signal based on the at least one control or information signal and a programmed computing device programmed to perform at least one function in response to the at least one control or information signal.